I am using the following script to extract internal and external links from web pages. I then another script to process those links according to my needs.

import requests
from urllib.parse import urlparse, urljoin
from bs4 import BeautifulSoup
import colorama

# init the colorama module
colorama.init()

GREEN = colorama.Fore.GREEN
GRAY = colorama.Fore.LIGHTBLACK_EX
RESET = colorama.Fore.RESET
YELLOW = colorama.Fore.YELLOW

# initialize the set of links (unique links)
internal_urls = set()
external_urls = set()

total_urls_visited = 0

def is_valid(url):
    """
    Checks whether `url` is a valid URL.
    """
    parsed = urlparse(url)
    return bool(parsed.netloc) and bool(parsed.scheme)


def get_all_website_links(url):
    """
    Returns all URLs that is found on `url` in which it belongs to the same website
    """
    # all URLs of `url`
    urls = set()
    soup = BeautifulSoup(requests.get(url).content, "html.parser")
    for a_tag in soup.findAll("a"):
        href = a_tag.attrs.get("href")
        if href == "" or href is None:
            # href empty tag
            continue
        # join the URL if it's relative (not absolute link)
        href = urljoin(url, href)
        parsed_href = urlparse(href)
        # remove URL GET parameters, URL fragments, etc.
        href = parsed_href.scheme   "://"   parsed_href.netloc   parsed_href.path
        if not is_valid(href):
            # not a valid URL
            continue
        if href in internal_urls:
            # already in the set
            continue
        if domain_name not in href:
            # external link
            if href not in external_urls:
                print(f"{GRAY}[!] External link: {href}{RESET}")
                external_urls.add(href)
            continue
        print(f"{GREEN}[*] Internal link: {href}{RESET}")
        urls.add(href)
        internal_urls.add(href)
    return urls


def crawl(url, max_urls=1000):
    """
    Crawls a web page and extracts all links.
    You'll find all links in `external_urls` and `internal_urls` global set variables.
    params:
        max_urls (int): number of max urls to crawl, default is 30.
    """
    global total_urls_visited
    total_urls_visited  = 1
    print(f"{YELLOW}[*] Crawling: {url}{RESET}")
    links = get_all_website_links(url)
    for link in links:
        if total_urls_visited > max_urls:
            break
        crawl(link, max_urls=max_urls)


if __name__ == "__main__":
    import argparse
    parser = argparse.ArgumentParser(description="Link Extractor Tool with Python")
    parser.add_argument("url", help="The URL to extract links from.")
    parser.add_argument("-m", "--max-urls", help="Number of max URLs to crawl, default is 30.", default=30, type=int)
    
    args = parser.parse_args()
    url = args.url
    max_urls = args.max_urls
    # domain name of the URL without the protocol
    domain_name = urlparse(url).netloc
    crawl(url, max_urls=max_urls)

    # save the internal links to a file
    with open(f"{domain_name}_internal_links.txt", "w") as f:
        for internal_link in internal_urls:
            print(internal_link.strip(), file=f)

    # save the external links to a file
    with open(f"{domain_name}_external_links.txt", "w") as f:
        for external_link in external_urls:
            print(external_link.strip(), file=f)

I have tested the script on numerous websites and it works fine. But after some time I get an error (many different errors) and the script stops.

For example:

requests.exceptions.InvalidSchema: No connection adapters were found for

Is there an error-agnostic way to keep the script running?

CodePudding user response：

requests.exceptions.InvalidSchema: No connection adapters were found for

Based on error info, you need to include the protocol schema, cause without the http:// or https:// part, requests is not able to connect to the remote server.

Try to print your requestet url in case of an error, to get specific information.

In newer code avoid old syntax findAll() instead use find_all() or select() with css selectors - For more take a minute to check docs